揭示大模型在上下文学习中元学习能力的多阶段电路演化过程
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
- 通过扩展拷贝任务构建上下文元学习场景，观察模型训练中的动态变化
- 发现元学习能力发展呈现多个阶段，每个阶段伴随独特电路结构的出现
- 为理解Transformer模型上下文学习的本质提供了新视角，适合研究大模型机制者
基于Transformer的语言模型展现出上下文学习（ICL）能力，即根据上下文自适应地做出预测。以往研究将归纳头与ICL关联，但仅能解释答案存在于上下文时的准确率跃升。然而，大模型在实际应用中更重要的特性是能从上下文中元学习如何解决问题，而非简单复制答案；这一能力如何在训练中获得仍不明确。本文通过实验分析模型在训练过程中电路的动态演化，揭示了该能力的获取机制。我们将先前的研究任务扩展至上下文元学习设置，要求模型从示例中推断任务并回答查询。有趣的是，在此设定下，我们发现模型获取该能力的过程包含多个阶段，且每个阶段均有独特的电路结构涌现，与归纳头的单阶段变化形成对比。这些电路的出现可与大模型中的多种现象关联，推动我们更深入理解Transformer模型实现上下文学习的内在根源。
原文摘要 · Abstract (English)
Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when the answer is included within the context. However, an important property of practical ICL in large language models is the ability to meta-learn how to solve tasks from context, rather than just copying answers from context; how such an ability is obtained during training is largely unexplored. In this paper, we experimentally clarify how such meta-learning ability is acquired by analyzing the dynamics of the model's circuit during training. Specifically, we extend the copy task from previous research into an In-Context Meta Learning setting, where models must infer a task from examples to answer queries. Interestingly, in this setting, we find that there are multiple phases in the process of acquiring such abilities, and that a unique circuit emerges in each phase, contrasting with the single-phases change in induction heads. The emergence of such circuits can be related to several phenomena known in large language models, and our analysis lead to a deeper understanding of the source of the transformer's ICL ability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。